docs(perception): record TLS and direct TCP latency attribution

docs/adr/0049-stream-first-perception-profiles.md

@@ -904,3 +904,23 @@ Do not equate complete output accounting with usable geometry/policy or autonomo
 readiness. Next instrument data-plane stage boundaries before optimizing remaining
 tails; no gate widening.245 local/202 Worker tests PASS,131 source hashes matched.
 [Detailed route and full-profile evidence](../../experiments/perception/PERCEPTION_STREAM_STAGE2_LAN_ROUTE_2026-09-02.md).
+
+## Stage 2 increment 18: application-edge transport attribution (2026-09-02)
+
+Optional bounded TLS-record witnesses belong to isolated diagnostic tooling, not
+the runtime route or model profile. A/B/A keeps the~100ms tail with and without
+the witnesses;424 ciphertext records match between edges and192 serial RPCs
+match their handlers.13 post-start long calls localize to request(8)/response(5)
+inter-edge transit, not local JSON/handler work. Startup without admitted clock
+mapping stays unqualified; timestamps are application receipt/drain, not wire ACKs.
+
+Direct TCP connects to the known Worker SSH port reproduce67.9–91.1ms peaks without
+gRPC, Docker or SSH forwarding. Both active links are Wi-Fi; native Worker loopback
+after startup is0.240–0.299ms. The specific radio/AP/OS/driver mechanism is unproved.
+Do not weaken5ms/125ms gates or replace models to address an external transport
+symptom. Conversely, this does not exonerate all application costs or qualify
+large scene buffers. Continue per-frame queue/serialization/publication attribution;
+an available wired comparison should remove both radio legs but is not a prerequisite
+for experimental runtime/standalone work. No product transport or GPU workload changed.
+82 local/82 Worker tests PASS;142 staged files exact; previous full-graph latency FAIL
+stands. [Detailed evidence](../../experiments/perception/PERCEPTION_STREAM_STAGE2_TLS_ATTRIBUTION_2026-09-02.md).